This project repository holds the source code developed for RateRL, using the network simulator 3 (ns-3), ns3-gym, json and TF-Agents 3rd party libraries. RateRL objective is to assist the researchers during the implementation and validation phases of RL-based RA algorithms in a standardised manner, to facilitate the comparison between algorithms for future solutions.
Copyright (C) 2023, INESC TEC. This project is licensed under the terms of the GNU General Public Licence (GPL) v3.0
This project is authored by:
- Ruben Queiros, Luis Ferreira, Helder Fontes, Rui Campos [INESC TEC, Portugal]
The instructions to set-up and run this framework are explained below.
To run RateRL with the default configuration, run the following command:
$ python start_script.py
Override configuration examples:
python start_script.py --simType train
python start_script.py --raAlg dara Specify simulation results directory name:
python start_script.py --dir example_name If you want to tweak the simulation, changing the Rate Adaptation Algorithm configured, as well as the Simulation Random Seed, consider the following Command Line Arguments:
If you would like to use this code, please cite it as follows:
- TODO Update with ArXiv